© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 27129
    Prev
    Next
    INDEX
    Explanations

    colons followed by numerical data or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    estre
    -0.07
    ="{!!
    -0.07
    ÙĪØ´
    -0.06
    761
    -0.06
    ìķĶ
    -0.06
    earer
    -0.06
    ÑĨен
    -0.06
    .study
    -0.06
     cape
    -0.06
     Phon
    -0.06
    POSITIVE LOGITS
    -mask
    0.07
    æŀĿ
    0.06
     business
    0.06
    æĶ¯
    0.06
    è²
    0.06
     Troy
    0.06
    iode
    0.06
     Biz
    0.06
    isle
    0.06
    ursal
    0.06
    Activations Density 0.000%

    No Known Activations